docs(update-notes): format <think> reasoning tags for consistency in OpenAI-compatible providers

Author: hannesrudolph

docs/update-notes/v3.30.0.mdx

@@ -40,7 +40,7 @@ OpenRouter currently supports 7 embedding models, including the top‑ranking Qw
 ## Provider Updates
 
 * Chutes: dynamic/router provider so new models appear automatically; safer error logging and temperature applied only when supported ([#8980](https://github.com/RooCodeInc/Roo-Code/pull/8980))
-* OpenAI‑compatible providers: handle <think> reasoning tags in streaming for consistent reasoning chunk handling ([#8989](https://github.com/RooCodeInc/Roo-Code/pull/8989))
+* OpenAI‑compatible providers: handle `<think>` reasoning tags in streaming for consistent reasoning chunk handling ([#8989](https://github.com/RooCodeInc/Roo-Code/pull/8989))
 * GLM 4.6: capture reasoning content in base OpenAI‑compatible provider during streaming ([#8976](https://github.com/RooCodeInc/Roo-Code/pull/8976))
 * Fireworks: add GLM‑4.6 to the model dropdown for stronger coding performance and longer context (thanks mmealman!) ([#8754](https://github.com/RooCodeInc/Roo-Code/pull/8754))
 * Fireworks: add MiniMax M2 with 204.8K context and 4K output tokens; correct pricing metadata (thanks dmarkey!) ([#8962](https://github.com/RooCodeInc/Roo-Code/pull/8962))

docs/update-notes/v3.30.mdx

@@ -40,7 +40,7 @@ OpenRouter currently supports 7 embedding models, including the top‑ranking Qw
 ## Provider Updates
 
 * Chutes: dynamic/router provider so new models appear automatically; safer error logging and temperature applied only when supported ([#8980](https://github.com/RooCodeInc/Roo-Code/pull/8980))
-* OpenAI‑compatible providers: handle <think> reasoning tags in streaming for consistent reasoning chunk handling ([#8989](https://github.com/RooCodeInc/Roo-Code/pull/8989))
+* OpenAI‑compatible providers: handle `<think>` reasoning tags in streaming for consistent reasoning chunk handling ([#8989](https://github.com/RooCodeInc/Roo-Code/pull/8989))
 * GLM 4.6: capture reasoning content in base OpenAI‑compatible provider during streaming ([#8976](https://github.com/RooCodeInc/Roo-Code/pull/8976))
 * Fireworks: add GLM‑4.6 to the model dropdown for stronger coding performance and longer context (thanks mmealman!) ([#8754](https://github.com/RooCodeInc/Roo-Code/pull/8754))
 * Fireworks: add MiniMax M2 with 204.8K context and 4K output tokens; correct pricing metadata (thanks dmarkey!) ([#8962](https://github.com/RooCodeInc/Roo-Code/pull/8962))